© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15584
    Prev
    Next
    INDEX
    Explanations

    subtropical or tropical forests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ara
    -0.08
    rego
    -0.07
    rez
    -0.07
    beren
    -0.07
    ocas
    -0.07
    ç¦ģ
    -0.07
     Inscription
    -0.07
    bett
    -0.07
    ä¸įèIJ½
    -0.07
    æĵĤ
    -0.07
    POSITIVE LOGITS
     unspecified
    0.08
    大类
    0.07
    ä¸įå¾Ĺ
    0.07
     miscellaneous
    0.07
    åŃIJç±»
    0.07
     except
    0.06
    âĢ¦
    0.06
     subclasses
    0.06
     Except
    0.06
    .decorators
    0.06
    Activations Density 0.041%

    No Known Activations